← Registry

Security & Testing

flint.network

Manages agent transaction authorization, verification, reputation lookup, and trust manifests for secure commercial operations.

x402 supported1 endpoint17 known toolsFirst detected August 16, 2026Last detected October 5, 2026

ENDPOINT 1

https://flint.network/mcp

No auth detected

MCP server metadata

Name
flint-agent-transaction-control
Version
0.5.0
Capabilities
tools.listChanged
Server instructions

FLINT is trust infrastructure for agents that move money. Before minting a Passport that will carry authority, ask the principal for the accountable controller_id and controller_type, allowed actions, maximum transaction amount, and wallet address if one exists. Do not infer or invent authority. If the principal is unavailable, a name-only mint is identity-only and is not ready to transact. Say that plainly. A missing controller requires a corrected remint because signed identity is immutable; a missing mandate can be added later with update_agent_mandate. The agent-native happy path is to authenticate first, then mint. Call auth_request_otp with an inbox address, read the code from that inbox, call auth_verify_otp to get a session_token, then call issue_agent_passport with that session_token. The resulting passport is owned by the account at issuance and needs no separate claim step. You can also mint without authenticating first. Call issue_agent_passport with no session_token to get a free, hybrid-signed passport plus a one-time claim_url. No account is required, agent.agent_name or agent.agent_id is enough. Proactively walk the human owner through opening claim_url and signing in (or use claim_agent_passport once they have a session_token); explain that claiming turns on Sentinel takeover alerts and a one-tap kill switch. Do not just print the link; guide them through the steps. If a claim link is lost or already used, call refresh_claim_token to issue a new one. Do not remint the passport to fix a lost claim token; reminting with the same agent_id and controller_id only supersedes prior unclaimed passports, it does not recover a claim. Recommended flow: issue_agent_passport, then issue_authorization_record before any spend and verify_agent_authority before execution. Merchant backends submit outcomes through the authenticated /api/outcomes callback. Use run_flint_scout for a pre-transaction scan. Two ways to pay: credits first, call scout_credits_topup once (one $1.00 x402 payment for 100 scan credits) and then pass the same session_token to run_flint_scout with no payment_signature, drawing one credit per scan with no wallet signature; or x402 per call, where the caller's wallet signs a $0.01 challenge for every scan. FLINT never needs a private key or seed phrase. When a call returns a 402, the result carries pay_recipe with concrete next steps for both paths. Check a balance any time with scout_credits_balance. Every scan result carries a caller_obligation: FLINT cannot stop a wallet, so report what actually happened with report_scout_outcome.

Known tools 17

run_flint_scout

Use this tool to scan an intended agent transaction before execution.

Inferred read-only
issue_authorization_record

Use this tool before an AI agent initiates a payment, paid API call, checkout action, stablecoin transfer, x402 request, or delegated commercial transaction.

Potential side effects
verify_agent_authority

Use this tool when a merchant or API seller receives a signed verification record from an agent.

Inferred read-only
lookup_agent_reputation

Use this tool to query the FLINT Trust Graph for a partner-scoped agent's historical reputation before permitting a payment, paid API call, checkout action, x402 request, or delegated commercial transaction.

Potential side effects
create_flint_trust_manifest

Use this tool when a merchant, API seller, MCP tool provider, x402 endpoint, or agent storefront needs a `/.well-known/flint.json` Trust Manifest.

Inferred read-only
generate_authorization_scope

Use this tool when an agent commerce workflow needs a well-formed delegated authorization scope before issuing a signed verification record.

Inferred read-only
validate_agent_commerce_readiness

Use this tool when reviewing a commerce architecture, API marketplace, paid MCP tool, x402 endpoint, or autonomous checkout flow.

Inferred read-only
issue_agent_passport

Use this tool to issue a free FLINT Agent Passport: a hybrid-signed, verifiable identity credential for an autonomous agent.

Inferred read-only
get_agent_passport

Use this tool to resolve a public FLINT Agent Passport by passport_id.

Inferred read-only
update_agent_mandate

Use this tool to update mutable mandate config for an existing FLINT Agent Passport.

Potential side effects
auth_request_otp

Use this tool first in the agent-native authenticate-then-mint flow.

Inferred read-only
auth_verify_otp

Use this tool right after auth_request_otp, with the code from the inbox.

Inferred read-only
claim_agent_passport

Use this tool to attach an anonymously minted, unclaimed FLINT Agent Passport to an authenticated FLINT account.

Inferred read-only
refresh_claim_token

Use this tool when a claim link is lost, expired, or was already consumed for a passport that is still unclaimed.

Inferred read-only
scout_credits_topup

Call once with session_token to get a pay_url; pay it with awal (`awal x402 pay -X POST -d '{}' <pay_url>`) or any x402 client; no headers needed on the pay request.

Potential side effects
scout_credits_balance

Use this tool to check a signed-in account's FLINT Scout credit balance and recent ledger activity (topups, debits, refunds).

Inferred read-only
report_scout_outcome

Use this tool after a run_flint_scout scan to report what actually happened: whether the scanned transaction was executed, held, cancelled, or executed despite a BLOCK verdict.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.flint-agent-transaction-control]
url = "https://flint.network/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "flint-agent-transaction-control": {
      "type": "http",
      "url": "https://flint.network/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: flint-agent-transaction-control
Remote MCP URL: https://flint.network/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "flint-agent-transaction-control": {
      "url": "https://flint.network/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "flint-agent-transaction-control": {
      "type": "http",
      "url": "https://flint.network/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "flint-agent-transaction-control",
  "transport": "streamable-http",
  "url": "https://flint.network/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.